Transrectal ultrasound (TRUS) is a versatile and real-time imaging modality that is commonly used in image-guided prostate cancer interventions (e.g., biopsy and brachytherapy). Accurate segmentation of the prostate is key to biopsy needle placement, brachytherapy treatment planning, and motion management. Manual segmentation during these interventions is time-consuming and subject to inter- and intraobserver variation. To address these drawbacks, we aimed to develop a deep learning-based method which integrates deep supervision into a three-dimensional (3D) patch-based V-Net for prostate segmentation.We developed a multidirectional deep-learning-based method to automatically segment the prostate for ultrasound-guided radiation therapy. A 3D supervision mechanism is integrated into the V-Net stages to deal with the optimization difficulties when training a deep network with limited training data. We combine a binary cross-entropy (BCE) loss and a batch-based Dice loss into the stage-wise hybrid loss function for a deep supervision training. During the segmentation stage, the patches are extracted from the newly acquired ultrasound image as the input of the well-trained network and the well-trained network adaptively labels the prostate tissue. The final segmented prostate volume is reconstructed using patch fusion and further refined through a contour refinement processing.Forty-four patients' TRUS images were used to test our segmentation method. Our segmentation results were compared with the manually segmented contours (ground truth). The mean prostate volume Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), and residual mean surface distance (RMSD) were 0.92 ± 0.03, 3.94 ± 1.55, 0.60 ± 0.23, and 0.90 ± 0.38 mm, respectively.We developed a novel deeply supervised deep learning-based approach with reliable contour refinement to automatically segment the TRUS prostate, demonstrated its clinical feasibility, and validated its accuracy compared to manual segmentation. The proposed technique could be a useful tool for diagnostic and therapeutic applications in prostate cancer.
This paper compares various optimization methods for fuzzy inference system optimization. The optimization methods compared are genetic algorithm, particle swarm optimization and simulated annealing. When these techniques were implemented it was observed that the performance of each technique within the fuzzy inference system classification was context dependent.
247 Background: Dose escalation in prostate cancer (PCa) radiotherapy (RT) is limited by toxicity to surrounding tissue, including the rectum. Rectal spacers improve bowel toxicity in men treated with photons (i.e. IMRT). However, the relative benefit of rectal spacers in men treated with protons remains unknown. Further, proton therapy may result in high-dose exposure to the anterior rectal wall due to lateral penumbra with conventional opposed lateral beam arrangement. We hypothesize that rectal spacers will confer greater toxicity benefit in the setting of proton therapy compared with photon therapy. Methods: We conducted an IRB approved, single institution, retrospective review of patients receiving definitive conventional or moderate hypofractionated photon IMRT or pencil-beam scanning proton RT for localized PCa from 2018-2021. Four cohorts were compared: Photon with (Ph+RS) or without (Ph-RS) rectal spacer, and proton with (Pr+RS) or without (Pr-RS) rectal spacer. Rates of pelvic nodal treatment were equivalent between protons and photons within the +/- rectal spacer cohorts. Acute (<3 months) and late (≥ 3 month) toxicity was compared amongst the four cohorts. Cumulative incidence of physician-reported grade 1-2 gastrointestinal (GI) toxicity (CTCAE V5.0) was compared using Chi-square or Fisher’s exact test. Patient-reported bowel toxicity was evaluated using International Prostate Expanded Prostate Composite Index- Clinical Practice (EPIC-CP) and compared using linear mixed modeling. Results: 164 patients were eligible for analysis: 38 Ph-RS, 50 Ph+RS, 26 Pr-RS, & 50 Pr+RS. Median follow-up was 17.6 months. In men treated with protons, physician-reported acute G1-2 GI toxicity was significantly lower in men with versus without rectal spacer (6.12 vs 30.77%, Pr+RS vs Pr-RS, respectively; p=0.009) and there was a trend towards lower late G1-2 GI toxicity (8.51 vs 26.09%, Pr+RS vs Pr-RS, respectively; p=0.08). In men treated with photons, there were no significant differences in physician-reported acute or later GI toxicity with versus without rectal spacer. No significant differences in patient-reported outcomes were observed with versus without spacer in the proton or photon cohorts. Conclusions: Rectal spacer use was associated with a lower CTCAE grade 1-2 acute GI toxicity in men treated with protons, and this difference was not observed in men treated with photons. While this study is limited by low sample size, a relatively greater benefit of rectal spacer with proton vs. photon therapy was observed. Further prospective analyses in larger cohorts are ongoing to validate these hypothesis-generating findings.
254 Background: Ampullary carcinoma is a rare malignancy. Despite radical resection, survival rates remain low with high rates of local failure. To define the role of radiation therapy and chemotherapy with surgery, we performed a single institution analysis of treatment- related outcomes. Methods: A retrospective analysis was performed of all patients undergoing potentially curative therapy for adenocarcinoma of the ampulla of Vater at Duke University Hospitals between 1975 and 2009. Local control (LC), overall survival (OS), disease-free survival (DFS), and metastases-free survival (MFS) were estimated using the Kaplan-Meier Method. Results: One hundred thirty-seven patients with ampullary carcinoma underwent potentially curative pancreaticoduodenectomy. Sixty-one patients undergoing resection received adjuvant (n= 43) or neoadjuvant (n=18) radiation therapy with concurrent chemotherapy (CRT). Patients receiving radiotherapy were more likely to have poorly differentiated tumors. Median radiation dose was 50 Gy. Median follow up was 8.8 years. Of patients receiving neoadjuvant therapy, 67% were downstaged on final pathology with 28% achieving pathologic complete response. Three-year local control was significantly improved in patients receiving CRT (88% vs. 55% p= 0.001) with trend toward a 3-year OS benefit in patients receiving CRT (62% vs. 46% p=0.074). Despite this, there was no significant difference in 3-year DFS (66% CRT vs 48% surgery alone p=0.09) or MFS (69% CRT vs 63% surgery alone p=0.337). Conclusions: Long term survival rates are low. Local failure rates are high following radical resection alone and improved with CRT. Despite more adverse pathologic features in patients receiving CRT, survival outcomes were at least equivalent with a trend toward statistical significance. Given the patterns of relapse with surgery alone and local control benefit in patients receiving CRT, the use of chemoradiotherapy in selected patients should be considered. No significant financial relationships to disclose.
The COVID-19 pandemic altered the workplace for medical education. As restrictions ease, the opportunities provided by virtual rotations remain. Radiation oncology rotations based on virtual participation with patients (consultations, follow-ups, and brachytherapy), contouring and reviewing external beam plans, didactics, and unstructured office hours have been well received at multiple institutions. Virtual rotations decrease barriers to access including lack of a radiation oncology department at one's home institute and the high cost of travel and housing. Furthermore, rotations can be adapted to preclinical students and those with prior radiation oncology rotation experience. However, the virtual format creates and exacerbates several challenges including technical difficulties with electronic medical record or treatment planning software, lack of the spontaneous interactions common to in-person rotations, and unexpected delays in the clinic. We recommend early scheduled time with information technology services to troubleshoot any potential issues, scheduled office hours with faculty and videoconferencing with nonphysician team members to mitigate omission of in-person introductions, and provision of complete contact information for all staff scheduled to meet with students to facilitate communication when unexpected clinic issues arise. Although we are all excited for quarantine restrictions to safely be lifted, we support the continued development of virtual away rotations as a flexible, more affordable option to increase exposure to the field.
'%3e%3ccircle r='20' fill='%23008'/%3e%3ccircle r='17.5' fill='%23fff'/%3e%3ccircle r='3.5' fill='%23008'/%3e%3cg id='d'%3e%3cg id='c'%3e%3cg id='b'%3e%3cg id='a' fill='%23008'%3e%3ccircle r='.875' transform='rotate(7.5 -8.75 133.5)'/%3e%3cpath d='M0 17.5.6 7 0 2l-.6 5L0 17.5z'/%3e%3c/g%3e%3cuse xlink:href='%23a' transform='rotate(15)'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='rotate(30)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='rotate(60)'/%3e%3c/g%3e%3cuse xlink:href='%23d' transform='rotate(120)'/%3e%3cuse xlink:href='%23d' transform='rotate(-120)'/%3e%3c/g%3e%3c/svg%3e)